Antoinette’s Data Visualizations

Inspiration from here: https://freddybarragan.netlify.app/media/bayes/bayes_final.html

#  Read CSV File
csv_clean_data <- read_csv(here("data", "clean_data", "clean_data_ant", "transportation_clean_data_csv.csv"))
#  Read Shape File
transportation_clean_data <- st_read(here("data", "clean_data", "clean_data_ant", "transportation_clean_data_shp.shp"))

## Reading layer `transportation_clean_data_shp' from data source 
##   `C:\Users\atan\urban_gentrification\data\clean_data\clean_data_ant\transportation_clean_data_shp.shp' 
##   using driver `ESRI Shapefile'
## Simple feature collection with 56 features and 21 fields
## Geometry type: POLYGON
## Dimension:     XY
## Bounding box:  xmin: -74.04171 ymin: 40.5706 xmax: -73.85568 ymax: 40.7394
## Geodetic CRS:  NAD83

#  Replace Column abbr Names in Shape File with full name from CSV
colnames(transportation_clean_data) <- colnames(csv_clean_data)


transit_points <- st_read(here("data", "clean_data", "clean_data_ant", "transit_points.shp"))

## Reading layer `transit_points' from data source 
##   `C:\Users\atan\urban_gentrification\data\clean_data\clean_data_ant\transit_points.shp' 
##   using driver `ESRI Shapefile'
## Simple feature collection with 169 features and 1 field
## Geometry type: POINT
## Dimension:     XY
## Bounding box:  xmin: -74.03088 ymin: 40.57613 xmax: -73.86505 ymax: 40.73135
## Geodetic CRS:  NAD83

subway_map <- transportation_clean_data %>%
  ggplot() +
  geom_sf(aes(fill = sub_count), color = "#8f98aa") +
  geom_sf(data = transit_points, size = 1.5) +
  scale_fill_gradientn(colors=c("#FCF5EE","#b5cbcf","#55717b","#0a4260"), na.value="#D6D6D6") +
  # https://www.color-hex.com/color-palette/100132
  theme_minimal() +
  ggtitle("Subway Count \nby Neighborhood")+ 
  theme(axis.text = element_blank(),
        panel.grid.major = element_line("transparent"),
        plot.title = element_text(size = 40, face = "bold", hjust=.5),
        legend.key.width = unit(.5, "in"),
        legend.title = element_text(size = 25, face="bold", family="DIN Condensed"), 
        legend.position = "bottom" ,
        legend.text = element_text(size = 20, face="bold", family="DIN Condensed"))+
  guides(fill = guide_colourbar(title = "Number of Subway Stations", title.position="top", title.hjust = 0.5))

rent_map <- transportation_clean_data %>%
  ggplot() +
  geom_sf(aes(fill = mean_rent), color = "#8f98aa") +
  geom_sf(data = transit_points, size = 1.5) +
  scale_fill_gradientn(colors = c("#FCF5EE","#beafc2", "#8155ba", "#695e93")) +
  # https://www.color-hex.com/color-palette/1044873
  theme_minimal() +
  ggtitle("Mean Rent \nby Neighborhood")+ 
  theme(axis.text = element_blank(),
        panel.grid.major = element_line("transparent"),
        plot.title = element_text(size = 40, face = "bold", hjust=.5),
        legend.key.width = unit(.5, "in"),
        legend.title = element_text(size = 25, face="bold", family="DIN Condensed"), 
        legend.position = "bottom" ,
        legend.text = element_text(size = 20, face="bold", family="DIN Condensed"))+
    guides(fill = guide_colourbar(title = "Dollars", title.position="top", title.hjust = 0.5))

evict <- transportation_clean_data %>%
  ggplot() +
  geom_sf(aes(fill = eviction_count), color = "#8f98aa")+
  geom_sf(data = transit_points, size = 1.5) +
  scale_fill_gradientn(colors = c("#FCF5EE", "#cce2cb", "#b6cfb6","#97c1a9")) +
  # https://www.color-hex.com/color-palette/1044832
  theme_minimal() +
  ggtitle("Eviction Counts \nby Neighborhood")+ 
  theme(axis.text = element_blank(),
        panel.grid.major = element_line("transparent"),
        plot.title = element_text(size = 40, face = "bold", hjust=.5),
        legend.key.width = unit(.5, "in"),
        legend.title = element_text(size = 25, face="bold", family="DIN Condensed"), 
        legend.position = "bottom" ,
        legend.text = element_text(size = 20, face="bold", family="DIN Condensed"))+
  guides(fill = guide_colourbar(title = "Number of Evictions", title.position="top", title.hjust = 0.5))

noncit <- transportation_clean_data %>%
  ggplot() +
  geom_sf(aes(fill = noncitizen_perc), color = "#8f98aa") +
  geom_sf(data = transit_points, size = 1.5) +
  scale_fill_gradientn(colors = c("#FCF5EE","#ead1dc", "#d5a6bd", "#c27ba0")) +
  # https://www.color-hex.com/color-palette/1044826
  theme_minimal() +
  ggtitle("Immigrant Density \nby Neighborhood")+ 
  theme(axis.text = element_blank(),
        panel.grid.major = element_line("transparent"),
        plot.title = element_text(size = 40, face = "bold", hjust=.5),
        legend.key.width = unit(.5, "in"),
        legend.title = element_text(size = 25, face="bold", family="DIN Condensed"), 
        legend.position = "bottom" ,
        legend.text = element_text(size = 20, face="bold", family="DIN Condensed"))+
  guides(fill = guide_colourbar(title = "Percent Non-Citizen", title.position="top", title.hjust = 0.5))

ggarrange(subway_map, rent_map,evict, noncit,
          ncol=2, nrow=2, padding = unit(3,
  "line"))

white <- transportation_clean_data %>%
  ggplot() +
  geom_sf(aes(fill = white_perc), color = "#8f98aa") +
  geom_sf(data = transit_points, size = 1.5) +
  scale_fill_gradientn(colors = c("#FCF5EE","#919BB6", "#5A6687", "#3D465C")) +
  theme_minimal() +
  ggtitle("White Population \nby Neighborhood")+ 
  theme(axis.text = element_blank(),
        panel.grid.major = element_line("transparent"),
        plot.title = element_text(size = 40, face = "bold", hjust=.5),
        legend.key.width = unit(.5, "in"),
        legend.title = element_text(size = 25, face="bold", family="DIN Condensed"), 
        legend.position = "bottom" ,
        legend.text = element_text(size = 20, face="bold", family="DIN Condensed"))+
    guides(fill = guide_colourbar(title = "Percent White", title.position="top", title.hjust = 0.5))

black <- transportation_clean_data %>%
  ggplot() +
  geom_sf(aes(fill = black_perc), color = "#8f98aa") +
  geom_sf(data = transit_points, size = 1.5) +
  scale_fill_gradientn(colors = c("#FCF5EE","#F8ABA6", "#F58581", "#DB3F37")) +
  theme_minimal() +
  ggtitle("Black Population \nby Neighborhood")+ 
  theme(axis.text = element_blank(),
        panel.grid.major = element_line("transparent"),
        plot.title = element_text(size = 40, face = "bold", hjust=.5),
        legend.key.width = unit(.5, "in"),
        legend.title = element_text(size = 25, face="bold", family="DIN Condensed"), 
        legend.position = "bottom" ,
        legend.text = element_text(size = 20, face="bold", family="DIN Condensed"))+
    guides(fill = guide_colourbar(title = "Percent Black", title.position="top", title.hjust = 0.5))

asian <- transportation_clean_data %>%
  ggplot() +
  geom_sf(aes(fill = asian_perc), color = "#8f98aa") +
  geom_sf(data = transit_points, size = 1.5) +
  scale_fill_gradientn(colors = c("#FCF5EE","#C1C5EC", "#A1A8E2", "#4451C5"),                      
                       guide = guide_colourbar(title = "Percent Asian")) +
  theme_minimal() +
  ggtitle("Asian Population \nby Neighborhood")+ 
  theme(axis.text = element_blank(),
        panel.grid.major = element_line("transparent"),
        plot.title = element_text(size = 40, face = "bold", hjust=.5),
        legend.key.width = unit(.5, "in"),
        legend.title = element_text(size = 25, face="bold", family="DIN Condensed"), 
        legend.position = "bottom" ,
        legend.text = element_text(size = 20, face="bold", family="DIN Condensed"))+
    guides(fill = guide_colourbar(title = "Percent Asian", title.position="top", title.hjust = 0.5))

latinx <- transportation_clean_data %>%
  ggplot() +
  geom_sf(aes(fill = latinx_perc), color = "#8f98aa")+
  geom_sf(data = transit_points, size = 1.5) +
  scale_fill_gradientn(colors = c("#FCF5EE","#F4E2B8", "#E9C572", "#E77E2F")) +
  theme_minimal() +
  ggtitle("Latinx Population \nby Neighborhood")+ 
  theme(axis.text = element_blank(),
        panel.grid.major = element_line("transparent"),
        plot.title = element_text(size = 40, face = "bold", hjust=.5),
        legend.key.width = unit(.5, "in"),
        legend.title = element_text(size = 25, face="bold", family="DIN Condensed"), 
        legend.position = "bottom" ,
        legend.text = element_text(size = 20, face="bold", family="DIN Condensed"))+
  guides(fill = guide_colourbar(title = "Percent Latinx", title.position="top", title.hjust = 0.5))

ggarrange(subway_map, white, black, latinx, asian, 
          ncol=3, nrow=2, padding = unit(3,
  "line"))

gg <- ggplot(transportation_clean_data) +
  geom_sf(fill = "antiquewhite") +
  theme_minimal() +
  ggtitle("Neighborhood Names") +
  geom_sf_label_interactive(aes(label = NTAName, tooltip = NTAName),
                            size = 1.5) + 
  theme(panel.background = element_rect(fill = "aliceblue"),
        axis.title=element_blank(),
        axis.text = element_blank(),
        axis.text.y = element_blank(),
        axis.ticks = element_blank(),
        panel.grid.major = element_blank(),
        plot.title = element_text(size = 20, face = "bold", hjust=.5),
        )

girafe(ggobj = gg)

Madie’s Data Visualizations

Number of Qualified Units per Borough for each Tax Exemption Type

residential_developments = read_csv(here("data", "clean_data", "clean_data_madie","residential_developments.csv"))

ggplot(residential_developments, aes(x=tax_type, y = units, fill=borough))+
  geom_col(position="dodge") +
  scale_fill_manual(values = c("#F58581", "#E9C572", "#97c1a9", "#4451C5","#8155ba")) +
  labs(x="Tax Exemption Type",y= "Number of Units per Borough", title="Units per Borough Qualified for Property Tax Exemption Completed (2010-2020)") +
  theme(plot.title = element_text(size = 10, face = "bold", hjust=.5),
        legend.title = element_text(size = 10, face = "bold")) 

Low Income compared with 421a Qualified Units per borough

units_low_income_421a = read_csv(here("data", "clean_data", "clean_data_madie","units_low_income_421a.csv"))

ggplot(units_low_income_421a, aes(x=borough,y=value, fill=unit_type)) + 
  geom_bar(stat="identity", position="identity", alpha=.5)+
  scale_fill_manual(values = c("#F58581", "#4451C5")) +
  labs(x="Borough", y="Number of Units", title="Low Income and 421a Qualified Units per Borough (2010-2020)", color="Unit Type") +
  theme(plot.title = element_text(size = 11, face = "bold"),
        legend.title = element_text(size = 10, face = "bold"))

Median Gross Rent by Borough

borough_median_rent = read_csv(here("data", "clean_data", "clean_data_madie", "borough_median_rent.csv"))

ggplot(borough_median_rent, aes(x=year, y=value, color=Name, group=Name))+
  geom_point(size = 2)+
  geom_line(size=1)+
  scale_color_manual(values = c("#F58581", "#E9C572", "#97c1a9", "#4451C5","#8155ba")) +
  labs(x="Year", y="Rent ($)", title="Median Gross Rent by Borough (2006-2021)") +
  theme(plot.title = element_text(size = 15, face = "bold"),
        legend.title = element_text(size = 10, face = "bold"))

Median Gross Rent by Brooklyn Community Districts

brooklyn_median_rent = read_csv(here("data", "clean_data", "clean_data_madie","brooklyn_median_rent.csv"))

# Filter data for year 2021
brooklyn_median_rent_2021 <- brooklyn_median_rent %>%
  filter(year == 2021)

# Identify the 10 names with the highest rent values in 2021
top_10_names <- brooklyn_median_rent_2021 %>%
  arrange(desc(rent)) %>%
  slice_head(n = 10) %>%
  pull(Name)

# Filter original data for the top 10 names
brooklyn_median_rent_top_10 <- brooklyn_median_rent %>%
  filter(Name %in% top_10_names)

ggplot(brooklyn_median_rent_top_10, aes(x=year, y=rent, group=Name, color=Name)) +
  geom_point(size=2)+
  geom_line(size=1)+
  scale_color_manual(values=c("#F58581", "#E9C572", "#97c1a9", "#4451C5","#8155ba", "#c27ba0", "#E77E2F", "#8155ba", "#415d43", "#474973")) +
  labs(x="Year", y="Median Rent($)", title="Median Gross Rent by Neighborhood in Brooklyn (2006-2021)", col = "Neighborhood") +
  theme(legend.title = element_text(size = 10, face = "bold"), 
               legend.text = element_text(size = 7),
        plot.title = element_text(size = 11, face = "bold"))

diff_median_rent = read_csv(here("data", "clean_data", "clean_data_madie","diff_median_rent.csv"))

ggplot(diff_median_rent, aes(x=unit_nums, y=diff)) +
  geom_point(alpha=0.8, color = "#8155ba") + 
  geom_smooth(method="lm", se=FALSE, color = "#4451C5") + 
  geom_label_repel(label=diff_median_rent$Name, size = 2.5) +
  labs(x="Number of 421a Units", y="Median Rent Increase($)", title="Linear Model of 421a Units Number and Median Rent Increase") +
  theme(plot.title = element_text(size = 13, face = "bold"),
        legend.title = element_text(size = 10, face = "bold"))

Cara’s Data Visualizations

# Load Brooklyn gentrification census tract shp file
shapefile <- st_read(here("data", "clean_data", "clean_data_cara", "bk_gent_levels.shp"))

## Reading layer `bk_gent_levels' from data source 
##   `C:\Users\atan\urban_gentrification\data\clean_data\clean_data_cara\bk_gent_levels.shp' 
##   using driver `ESRI Shapefile'
## Simple feature collection with 743 features and 14 fields
## Geometry type: MULTIPOLYGON
## Dimension:     XY
## Bounding box:  xmin: 972624.9 ymin: 147001.4 xmax: 1024287 ymax: 208551.2
## Projected CRS: NAD83 / New York Long Island (ftUS)

# Create list of color values for Brooklyn choropleth
val <- c("#d8d5e8", "#aa93cb", "#005b6e","#8068a6", "#f9ce70","#ffaf5a" ,"#d64e00","#730000")

# Create Brooklyn gentrification level choropleth
ggplot(shapefile) +
  geom_sf(aes(fill = Ty_1_19)) +
  theme_void() +
  theme(panel.grid = element_line(color = "transparent")) +
  labs(title = "What areas have a high risk of gentrification?", fill="Gentrification Level") + 
  theme(plot.title = element_text(size = 14, face = "bold"),
        legend.title = element_text(size = 10, face = "bold")) +
  scale_fill_manual(values=val,
                    breaks = c("LI - Not Losing Low-Income Households",
                               "LI - At Risk of Gentrification",
                               "LI - Ongoing Displacement of Low-Income Households",
                               "LI - Ongoing Gentrification",
                               "MHI - Advanced Gentrification",
                               "MHI - Stable Exclusion",
                               "MHI - Ongoing Exclusion",
                               "VHI - Super Gentrification or Exclusion" ),
                    labels = c("Not Losing Low-Income Households", 
                                "At Risk of Gentrification", 
                               "Ongoing Displacement of Low-Income Households", 
                              "Ongoing Gentrification", 
                                "Advanced Gentrification", 
                               "Stable Exclusion", 
                                "Ongoing Exclusion", 
                                "Super Gentrification or Exclusion"))

# Read clean csv file of Brooklyn census tract gentrification levels
redlining_long <- read_csv(here("data", "clean_data", "clean_data_cara","bk_redlining_long.csv"), show_col_types = FALSE)

# Plot barchart showing districts and their hazardous and declining levels
ggplot(redlining_long, aes(x = boro_cd, y = Percent_value, fill = Category, label= Percent_value_label)) +
  geom_bar(stat = "identity") +
  geom_text(size = 2.5, position = position_stack(vjust = 0.5)) +
  coord_flip() +
  scale_fill_manual(values = c("#F58581", "#4451C5"), name = "Classification", labels = c("Declining", "Hazardous")) +
  labs(y = "Percent", x="Community District", title="Redlining in Brooklyn") +
  theme(plot.title = element_text(size = 10, face = "bold"),
        legend.title = element_text(size = 10, face = "bold"))

# Read clean csv file of NYC's public housing developments
public_dev <- read_csv(here("data", "clean_data", "clean_data_cara", "bk_public_developments.csv"), show_col_types = FALSE)
# Plot barchart of public housing across boroughs
ggplot(public_dev, aes(x = fct_infreq(BOROUGH))) + 
geom_bar(stat = "count", fill = "#A1A8E2", color = "black")+
labs(x="Borough", y="Development Count", title="Public Housing Developments Per Borough") +
  theme(plot.title = element_text(size = 14, face = "bold"))

# Convert the public housing dataframe to an sf object
sf_df <- st_as_sf(public_dev, wkt = "the_geom")

# Create interactive map showing nyc public housing developments
leaflet() %>%
  addTiles() %>%
  addPolygons(data = sf_df,
              fillColor = "purple",
              fillOpacity = 1,
              color = "purple",
              stroke = TRUE,
              weight = 1,
              popup = ~the_geom,
              label=~DEVELOPMEN) %>%
  addFullscreenControl()

Grant’s Data Visualizations

# Load Brooklyn gentrification census tract shp file
property_value_growth <- read_csv(here("data", "clean_data", "clean_data_grant", "property_value_growth.csv"))

ggplot(property_value_growth %>% filter(neighborhood == "GREENPOINT" | neighborhood == "BEDFORD STUYVESANT") %>% mutate(date_diff_days = date_diff / 86400) %>% filter(date_diff_days > 60), aes(x=`date_diff_days`, price_diff))+
  geom_point(color = "#A1A8E2")+
  geom_smooth(color = "black")+
  facet_wrap(~neighborhood)+
  labs(title = "Property Appreciation By Hold Time", x = "Time Held (days)", y = "Appreciation ($)")+
  scale_y_continuous(trans='log10') +
  theme(plot.title = element_text(size = 13, face = "bold"))

ggplot(property_value_growth %>% filter(neighborhood == "GREENPOINT" | neighborhood == "BEDFORD STUYVESANT") %>% mutate(date_diff_days = date_diff / 86400), aes(x=`date_diff_days`))+
  geom_histogram(binwidth = 90, fill = "#A1A8E2", color = "black")+
  facet_wrap(~neighborhood)+
  labs(title = "Property Hold Times", x = "Time Held (days)", y = "Sales Count") +
  theme(plot.title = element_text(size = 14, face = "bold"))

# Merwan’s Data Visualizations

x <- read_csv(here("data", "clean_data", "clean_data_merwan", "NYC_Gentrification_2000_16_clean.csv"))
housing <- read_csv(here("data", "clean_data", "clean_data_merwan", "HousingDB_post2010_clean.csv"))
housing$Ownership <- as.factor(housing$Ownership)
housing$Job_Type <- as.factor(housing$Job_Type)
housing$Borough <- as.factor(housing$Borough)

ggplot(data=x[order(x$NHWPCTDIFF, decreasing=TRUE)[0:100],], aes(x=Borough)) +
  geom_bar(fill = "#A1A8E2", color = "black") +
  labs(y="Change in % Non-Hispanic White", 
       title="100 Census Tracts with Greatest Difference in % Non-Hispanic White Pop. by Borough") +
  theme(plot.title = element_text(size = 11, face = "bold"))

ggplot(data=housing[housing$Borough=='Brooklyn',], aes(x=PermitYear, fill=Job_Type)) +
  geom_bar() +
  scale_fill_manual(values=c("#F58581","#97c1a9", "#4451C5"))+
  labs(title="Job Type Breakdown per Borough per Year", x="Permit Year", y="Count") +
  theme(plot.title = element_text(size = 12, face = "bold"),
        legend.title = element_text(size = 10, face = "bold"))

gov_housing = housing[housing$`Ownership Abbrev`=='Government, City',]
gov_housing = gov_housing[gov_housing$Borough != "Staten Island",]
ggplot(data=gov_housing[gov_housing$Job_Type=='New Building',], aes(x=PermitYear, fill=Ownership)) +
    labs(title="Ownership of Government Housing", x="Permit Year", y="Cnt") +
  geom_bar() +
  scale_fill_manual(values=c("#F58581", "#E9C572", "#97c1a9", "#4451C5","#8155ba", "#c27ba0", "#E77E2F", "#8155ba", "#415d43", "#474973", "#c1121f")) +
  facet_wrap(~Borough, scales='free', ncol=2) +
  theme(plot.title = element_text(size = 12, face = "bold"),
        legend.title = element_text(size = 10, face = "bold"))

individ_housing = housing[housing$`Ownership Abbrev`=='Private For-Profit',]
individ_housing = individ_housing[individ_housing$Borough != "Staten Island",]
ggplot(data=individ_housing[individ_housing$Job_Type=='New Building',], aes(x=PermitYear, fill=`Ownership`)) +
  geom_bar(position='fill') +
  scale_fill_manual(values=c("#F58581", "#E9C572", "#97c1a9", "#4451C5","#8155ba", "#c1121f"))+
  labs(title="Ownership of Private For-Profit Housing", x="Permit Year", y="Cnt") +
  facet_wrap(~Borough, ncol=2, scales = 'free') +
  theme(plot.title = element_text(size = 12, face = "bold"),
        legend.title = element_text(size = 10, face = "bold"))